Hi statistic analysis for biomedical application is not so simple....I should know the biological problem to find the right statistical solution.Which type of software do you use for the statistical analysis? I would advise you to use SigmaPlot. if you want you can try to send me a table with your data because i have not so clear your statistical problem.. but if you must compare 2 different population with a different "n" you must check at first the Normality Test (Shapiro-Wilk) of your population. See you

This would all depend on your normal distribution. If you do have a normal distribution i would recomond a Sample T test. A 2 sample Test is used to find the difference between the arguments. Personally i would use the 2 sample T test. I know you will get the results you are looking for with that test. Also if you a software called Mini Tab, it will make it much easier to do a 2 sample T test. Good luck

hm... My statistics handbook says to me that we can use paired t-test if our 2 data sets is taken from 1 sample of objects. Since you have 2 data sets for 2 different samples, you have to use independent t-test. Sorry for my ugly English :(

2 sample test or student t test to test for mean differences between case and control would be more appropriate. Paired sample tests imply repeated observations (more or less). If your groups are somewhat homogeneous (implied by the age-sex-matched) then a 2 sample test is fine.

Hi colleague.

I understant from your case that you have a 1 treatment to compare to a control one , the appropriate test is Dunnett. Becase T-Test is used if you compare two treatements.

I think the independent 2 sample test should be used in this case. To be matched by sex and age only makes these 2 samples comparable and there is no need to adjust for those factors when it come to fit a model, but that doesn't make the 2 samples fit for a paired t test. An ideal situation for a paired t test is when every 2 samples are from one same subject. For example, samples are taken from a patient before and after a treatment.

Hi Jason,

The question about paired vs independent t-tests is not about sample size. The real concern is whether or not they are independent of one another. The fact that one group is twice as large as the other is not a concern unless it is a paired-sample experiment. If you really want to do a paired-comparison, see if you can match the groups on a common element (i.e., demographics, grades, etc).

Perhaps I've missed the point, but I do not see your concern about sample size and type of statistical analysis to perform.

You're absolutely right, Aaron. I did not mean to imply that doing some ex post facto matching would take care of any design problems.

The two sample t-test is the appropriate test; your setup does not meet the requirements for a paired t-test given the 2:1 matching. Enjoy.

Do the two-sample t-test. If there is a significant difference, you're good to go. It doesn't sound to me as though you have any criteria or variable for pairing the samples, anyway.

I agree with the above answers to use a two sample t-test... this can be two-tailed (if the parameter is subject to a positive or a negative change, like effect of a drug on serum lipids), or one tailed if the treatment leads only to a unidirectional change in data (like the effect of heating time on the change in temperature). You can't use a paired t-test unless your two data sets are taken from the same sample of subjects, for example: blood glucose values before and after drug treatment.

This sounds like a case control study, with controls matched with cases in a 2:1 ratio. But it seems that we don't have a categorical variable here with a yes or no but a continuous one. Am thinking out aloud here. I think our best bet would be to do an independent t-test on the two groups, and then report the results as controlled for by age and sex. Do not adjust by age and sex in a linear regression type analysis as it is already adjusted (matched, controlled, accounted).

Thank you for you comments. I also think independent sample t test is better. It is becasue SPSS also suggests pair-t test for match case, which triggers me to think in more details.

In SPSS Example for pair-t test.

In a study on high blood pressure, all patients are measured at the beginning of the study, given a treatment, and measured again. Thus, each subject has two measures, often called before and after measures. An alternative design for which this test is used is a matched-pairs or case-control study, in which each record in the data file contains the response for the patient and also for his or her matched control subject. In a blood pressure study, patients and controls might be matched by age (a 75-year-old patient with a 75-year-old control group member).

also in a reference http://www.spssvideotutor.com/paired-samples-t-test/

Thank Carl for suggesting me the generalized randomized block design!

The analysis that is appropriate for this randomized block design is neither a matched t-test nor an unmatched t-test, but rather a two-way analysis of variance. The two independent variables are patient vs. control which is a fixed effect with two levels, and the block, a random effect with separate levels for each set of matched subjects.

I think that the t-test for 2 independent t may be relevant if you the data satisfy the following assumptions:

1. The data classified as male and female.

2. Both males and females are normally distributed.

3. The variances of two groups are equal.

4. The independence between two groups(males and females)

The t-test for paired samples absolutely not relevant to you data. Please take care when you check assumption and notice that you have alternative tests(Non-parametric tests. I wish you all the best.

Since you are having a 1:2 ratio. Take the average of the control group which will give you case 1: contro 1 (average). Apply paired t-test now.

I agree with Carl Schwarz (mostly). But if the dependent variable is categorical (ordinal or dichotomous), other techniques may be needed to analyze this kind of data. It may be easyest to use loglinear models, which also allow for the use of (continuous) covariates. This can be done in SPSS. But there are various other possibilities (see Agresti, 2002).

Another problem which may make it necessary to use other techniques than a F-test (analysis of variance) or t-test

even when the dependent variable is continuous is eventual non-normallity of the dependent variable.

In such cases one may revert to nonparametric tests or to bootstrapping the parametric test statistic.

Agresti, A. (2002), Categorical data analysis, Second edition. Hoboken, NJ: Wiley.

You can used t-test for 2 group control : sex

I think t-test for 2 independent t may be most relevant kindly check the assumptions of the same....

Hi

independent 2 samples is better than other methods.

Muhammed Sollom is right.

It is clear that only independent sample test can apply but you have to screen your data for normality as to decide for a parametric or non-parametric test. Screen your data for normality using Kolmogorov Smirnov or Shapiro Wilk test. You can equally run case summaries statistics for case and control groups separately and compare the mean and the median for each subset. If the mean somehow overlaps with the median, the subsets are therefore normally or approximately normally distributed. Reinforce your assumption with Skewness and Kurtosis.

Regards.

If the two groups are matched then you dont need to account for sex and age, as they are matched. You have not said what it is that you are measuring?

Here your problem doesn't meet any assumptions to be satisfied by either of the t- tests. So either go for nonparametric version or if u r good at statistics go for modeling as suggested by Carl.J.

A comparison of two conditions is "randomized" if the assignment of a subject to a condition is the result of a random process. When randomization is applied within sets of similar subjects (called "blocks"), it is a randomized block design. In a case-control study, assignment to the case and control conditions is not random; matching creates blocks of similar subjects within which to select cases and controls. The design of this study is a case-control study with matching. A design that is not randomized has the enormous disadavantage that any observed difference between the conditions may be a result of differences between subjects that led to the non-random assignment, rather than the difference between conditions, per se. For example, if all severely sick patients are assigned to a more effective treatment with worse side effects, and all less sick patients are assigned to a less effective treatment with fewer side effects, the less effective treatment may have better results.

Despite the terms "Randomized" and "Design,", a "Generalized Randomized Block Design" does not refer to a randomized design for a study, but instead to an statistical analysis of blocking that may be employed for either a randomized or a non-randomized design. Thus results of the analysis of this study, using Generalized Randomized Block Design, must not be misinterpreted as having any benefit of randomization.

Personally, I think that perhaps the independent T test is preferable to this scenario. Because paired sample T test is

used to deal with the data with changes happened to every subject. By the way , I guess maybe ANOVA also suit to your

case. Anyway, you can have a try.

You should use independent t-test,

you can use pair t-test just if you want to compare this groups( just 2 group) :1- completely match your groups 2- to study twin 3- to study Couples 4- same groups in different variables or positions 5- same group that assess by different people.

Independent t-test that for your research

Testing, the normal distribution of the variables.

First check for normality of the data.If it is normally distributed go for independent sample t test.If not then you would have to go for a suitable non parametric test like Mann whitney test.If the data is not normally distributed other option is to log transform the data and then perform Independent sample t test.

As the data is matched there is no need for adjusting the scores.

Thanks Carl J very much for the explanation. You are very professional!!

statistical methods for numerical variable

there are two groups: 1. comparison group(T-test and ANOVA) 2. correlation and regression

t-test(paired and un paired )

UNPAIRED: the data are independent that is one nominal level variable (two different groups/categorical)with two group as independent variable that are mutually exclusive .eg. chomper mean birth weight between males and females

by independent of data we mean that the data value of each study subject rises independently uninfluenced by and uncorrelated with the data values of the other subjects. the distribution of the dependent variable /numerical variable normal(normally distributed). the test also assume that the variance (of the dependent variable) in the two groups are equal. the assumption is called the requirement of homogeneity of variance

PAIRED: data s are side to be paired , if the study subjects from one population can be matched or paired with particular subjects in the second population. paired data rise naturally from studies of twins and paired objects such as eyes or ears of the same individual.

advantage of paired data is that smaller size are needed b/c of the similarity , hence decries variability with in paired .paired data also arises in studies where observation are taken before and after the intervention on the same study subject.

paired data can be analysis the d/c b/n each member of the pair and tests to determine if the difference are significantly d/t from zero/ the data are normally distributed. eg. com paired mean blood pressure of diabetic patients before and after some intervention/treatment . one group matched twice rather than two independent group.

but your out come variable is categorical (case and control) not possible to use independent 2 samples or paired samples T test (it is wrong method of analysis)

The dependent /outcome/ response variable is categorical the appropriate method of analysis.

your out come variable is categorical , the baste method of analysis of your study or data is:

1. chi squared test of Independence( to check the association between categorical dependent variable and continuous or categorical independent variable)

2.matched paired test(cross-sectional , case control the data s are independent sample / before and after the study cross over or matched case control studies) each cell represent the number of pair in which both member of pair experienced the same value with the two equal to the number of pair

3. in paired sample we use MCNemar's test is the proper method of analysis to test the hypothesis

4. conditional logistic regression ( bi variate and multivariable analysis of logistic regression ) to check or to identify factors that affect the dependent variable(case and control) through controlled factors(independent variable) and confounding.the crud and a dusted OR together with the corresponding Confidence interval computed. A good fit as measured by Housmer lemeshow's test.

How to Select the Appropriate statistical Analise Selection criteria for statistical tests

First, you have to define the level of measurement of each variable to be included in the analysis.

Second, to select the correct statistical analysis, you have to clarify what you want to find out.

Third, sample size calculation or power analysis is directly related to the statistical test that is chosen.

The selection of a statistical test is based on the purpose of the test, the experimental design, and the type of variable (generally, measurement or rank).

You might consider discussing with a statistician. Without seeing your actual design, it's difficult to give wholesale advice. Off the cuff, I would say you might want to consider something like a mixed model or random components type design where you are interested in the marginal means but want to adjust for the matched analyses by including a random cluster/group effect in a linear model.

Firstly, even moderately skew, and hence non-Normal variables become more symmetrical when differenced in a matched analysis, so unless the data are very skew, the Central Limit Theorem comes into play even for modest-sized samples. If you use a standard t-test, the result would be unbiased in respect of the matching variable because the balance between cases and controls is retained. But you lose statistical power because the sample variance estimates in the denominator of t are inflated by a factor relating to the matching. More specifically, let x and y represent cases and controls respectively; then the simplest appropriate model if matching has an effect is

E(xr) = μ + θr, E(yr) = η + + θr. r = 1,2 ...n.

On H0, μ = η. Also θr ≠ θs, r ≠ s, and var(x) = var(y) = σ2. So

E Σ{xr – mean(x)}2 = (n-1)σ2 + Σ(θr – Θ)2, where Θ is the mean of the θr. Similarly for the sample estimate of var(y). If the θ’s vary substantially – sand if they do not, the matching is unnecessary – the denominator of t is much larger than it should be.

So your variable of analysis should be d = x – (y1 + y2)/2, because E(d) = μ + η, = 0 on H0 and

E Σ{dr – mean(d)}2 = (n-1)σ2 as it should be.

Sorry about the lack of subscripts in xr, yr etc and superscripts i the sums of squares - pasting my reply into the box got rid of them.

In a case control studies, where a person knows about the event of interest (case) is paired, or matched, with a person who does not have the event in control. Moreover, whether the exposure is associated with the event or not, hence we rely on matching to control for possible covariates, and we have the following cases:

--. In a 1:1 matched study, the matched set consists of one case and one control fromeach stratum, and it is most commonly used situation.

--. In a 1 : m matched study, the matched set consists of one case and m controls (in your case m is 2), and in general m lies between 2 and 5.

--In the m:n matched study, the matched set consists of n cases and with m controls and values of both (m and n) from 1 to 5.

For your study, 1 : 2 matched case-control study, you need to use 'The Proportional Hazard Regression Model'. For reference: see Breslow and Day (1980) and Collett (1991). Moreover, I have borrowed these ideas from:'Categorical Data Analysis Using the SAS System', by Maura E. Stokes, Charles S. Davis and Gary G. Koch.

I think that the T-test is used for the normal samples.

All methods will be acceptable, based on where you want to publish and what is your purpose of analysis. Some journals will accept an independent samples t-test and some will ask you to test for normality or use more sophisticated analysis (e.g. Proportional Hazard Regression Model). Think of all the assumptions also.

I suggest independent T-test or, maybe better, ANOVA or regression to take into account of sex and age.

If you want to compare some continuous value (say, Y) between cases and controls, the easiest approach is to fit a linear model with group as a factor (each group is the set of three values and group has as many levels as there are sets of three) and condition as another (condition has two levels) and Y as the response.

Hi

We provide low cost statistical data analysis service for student and researcher.

http://www.rdatascientists.com/p/data-analysis-service.html