You can use two-way Analysis of Variance to check the individual and combination effects.

Hello Mila,

It sounds as if you have a single independent variable, Rice Husk type, which has two levels (Physically activated; chemically activated). If by three parameters, you mean you have three different measures/scores, all of which relate to water purification performance, then it sounds to me as if you might wish to consider multivariate analysis of variance (1 IV; 3 DVs). There are, of course, other options, and manova does have some assumptions associated with it. However, without additional information, it's difficult to be more specific.

Good luck with your work.

Here are some of my data, hope you can help me

Hello again Mila,

The before/after rice husk adds a second factor, a repeated measures factor, to the design. With three samples per type (chemical vs. physical), the tests will not have good statistical power, unless the magnitude of the effects are very large.

But, it still looks to me as if a manova (one-between: treatment; one-within: occasion, aka before-after) with three dependent variables (pH, conductivity, TDS) is still a viable analytic choice.

If that's not sufficiently clear, perhaps there's someone at your institution with whom you could consult to move towards completion of your project.

Good luck with your work.

Thank you so much David Morse I really appreciate your effort in answering my queries.

I would caution against MANOVA because it's not what you think it is.

A lot of people assume that a MANOVA works like an ANOVA but with several outcome variables at once. This is not in the least bit true. MANOVA mashes your outcome variables together into composite outcome variables. And furthermore, it does it in a way that you cannot control. Instead of giving each outcome variable equal weighting, or even allowing you to decide on the relative importance of each variable, it basis the weighting on the relationship of each variable to the predictor variables. As Kendal Smith puts it ANOVA and MANOVA do not analyze the same variables and, thereby, address different research questions.

See

Huang FL. MANOVA: A procedure whose time has passed?. Gifted Child Quarterly. 2020 Jan;64(1):56-60.

Smith KN, Lamb KN, Henson RK. Making meaning out of MANOVA: the need for multivariate post hoc testing in gifted education research. Gifted Child Quarterly. 2020 Jan;64(1):41-55

More generally, Mila, I am worried that you are out here on ResearchGate asking questions that your supervisor should be helping you with. Analysis of water quality data has a number of pitfalls and problems, and you really need local expertise on your side.

As Ronán Michael Conroy said, MANOVA "mashes" your outcome variables together in a way you cannot control. What may not have been clear is that the manner in which it does that varies from sample to sample. In other words, if you did an exact replication of your study but with a new sample, the weights used to mash together the outcome variables would be different in the two studies. I.e., you would be analyzing different outcomes in the two studies.

I'll also add the 1989 classic by Huberty & Morris to his list of articles.

Article Multivariate Analysis Versus Multiple Univariate Analyses

HTH.

Bruce Weaver is right, and indeed I missed out the most important point of all (thank you, Bruce, for the kind words may not have been clear rather than fogot to say!). Not only does the mashup differ between studies, but since it's a function of the predictor variables, if you add a new predictor variable to the model (to adjust for a demographic variable, for example) the mashup variable also changes, so you cannot compare the models since they are not nested.

I also have a fundamental problem with MANOVA which has led to my never ever having used it : it's a vague hypothesis. Your study specifically measured three properties of water purification because you were interested in each of the three. They are three different things and there are three distinct questions to ask. They do not constitute three measures of the same construct but three dimensions of the construct of water quality.

Incidentally, since WHO standards exist, you can test your regression parameters against these.

While composing my earlier reply, I was trying to remember another thread where someone else had made the same point. A little digging this morning reminded me that it was Thom Baguley in this thread (where his reply is marked as the best reply).

https://www.researchgate.net/post/Lower_Type_I_error_risk_in_MANOVA_compared_with_ANOVA-why_is_it_the_case